Update app.py

app.py

@@ -1,12 +1,17 @@
 import gradio as gr
 from llama_cpp import Llama
 
-MODEL_PATH = "model.gguf"  # downloaded in advance
+MODEL_URL = "https://huggingface.co/bartowski/MegaBeam-Mistral-7B-512k-GGUF/resolve/main/MegaBeam-Mistral-7B-512k-Q4_K_M.gguf"
 
-llm = Llama(model_path=MODEL_PATH, n_ctx=8192, n_threads=4)
+llm = Llama(
+    model_path="model.gguf",
+    filename=MODEL_URL,
+    n_ctx=8192,
+    n_threads=4
+)
 
 def chat(prompt):
     response = llm(prompt, max_tokens=512, temperature=0.7)
     return response["choices"][0]["text"]
 
-gr.Interface(fn=chat, inputs="text", outputs="text", title="MegaBeam Mistral 512K - GGUF").launch()
+gr.Interface(fn=chat, inputs="text", outputs="text", title="MegaBeam Mistral 512K - GGUF").launch()